Using sliding concentric windows for license plate segmentation and processing

Anagnostopoulos, C; Anagnostopoulos, I; Tsekouras, G; Kouzas, G; Loumos, V; Kayafas, E

dc.contributor.author	Anagnostopoulos, C	en
dc.contributor.author	Anagnostopoulos, I	en
dc.contributor.author	Tsekouras, G	en
dc.contributor.author	Kouzas, G	en
dc.contributor.author	Loumos, V	en
dc.contributor.author	Kayafas, E	en
dc.date.accessioned	2014-03-01T02:43:45Z
dc.date.available	2014-03-01T02:43:45Z
dc.date.issued	2005	en
dc.identifier.issn	15206130	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31501
dc.subject	Character Recognition	en
dc.subject	Image Processing	en
dc.subject	Image Segmentation	en
dc.subject	Natural Scenes	en
dc.subject	Optical Character Recognition	en
dc.subject	Probabilistic Neural Network	en
dc.subject	Sliding Window	en
dc.subject	Neural Network	en
dc.subject.other	Algorithms	en
dc.subject.other	Cameras	en
dc.subject.other	License plates (automobile)	en
dc.subject.other	Lighting	en
dc.subject.other	Neural networks	en
dc.subject.other	Optical character recognition	en
dc.subject.other	Pattern matching	en
dc.subject.other	Topology	en
dc.subject.other	Algorithmic image processing	en
dc.subject.other	Multi font alphanumeric characters	en
dc.subject.other	Probabilistic Neural Network	en
dc.subject.other	Sliding concentric windows	en
dc.subject.other	Image segmentation	en
dc.title	Using sliding concentric windows for license plate segmentation and processing	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/SIPS.2005.1579889	en
heal.identifier.secondary	http://dx.doi.org/10.1109/SIPS.2005.1579889	en
heal.identifier.secondary	1579889	en
heal.publicationDate	2005	en
heal.abstract	In this paper, a new algorithm for vehicle license plate identification is proposed, on the basis of a novel adaptive image segmentation technique (Sliding Windows) in conjunction with a character recognition Neural Network. The algorithm was tested with 2820 natural scene gray level vehicle images of different backgrounds and ambient illumination. The camera focused on the plate, while the angle of view and the distance from the vehicle varied according to the experimental setup. The license plates properly segmented were 2719 over 2820 input images (96.4%). The Optical Character Recognition (OCR) system is a two layer Probabilistic Neural Network with topology 108-180-36, whose performance reached 97.4%. The PNN was trained to identify multi-font alphanumeric characters from car license plates based on data obtained from algorithmic image processing. © 2005 IEEE.	en
heal.journalName	IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation	en
dc.identifier.doi	10.1109/SIPS.2005.1579889	en
dc.identifier.volume	2005	en
dc.identifier.spage	337	en
dc.identifier.epage	342	en